LLM Online Spatial-temporal Signal Reconstruction Under Noise

TL;DR

This paper presents LLM-OSR, a novel framework combining Graph Signal Processing and Large Language Models for online spatial-temporal signal reconstruction, demonstrating robustness and accuracy under noisy conditions.

Contribution

The paper introduces a new GSP-LLM integrated framework for real-time spatial-temporal signal reconstruction, advancing noise robustness and prediction accuracy.

Findings

LLM-OSR outperforms existing methods under Gaussian noise.

GPT-4-o mini effectively predicts missing spatiotemporal data.

Framework demonstrates robustness across traffic and meteorological datasets.

Abstract

This work introduces the LLM Online Spatial-temporal Reconstruction (LLM-OSR) framework, which integrates Graph Signal Processing (GSP) and Large Language Models (LLMs) for online spatial-temporal signal reconstruction. The LLM-OSR utilizes a GSP-based spatial-temporal signal handler to enhance graph signals and employs LLMs to predict missing values based on spatiotemporal patterns. The performance of LLM-OSR is evaluated on traffic and meteorological datasets under varying Gaussian noise levels. Experimental results demonstrate that utilizing GPT-4-o mini within the LLM-OSR is accurate and robust under Gaussian noise conditions. The limitations are discussed along with future research insights, emphasizing the potential of combining GSP techniques with LLMs for solving spatiotemporal prediction tasks.